Claude Opus 4.5
Frontier model for coding, computer use, long-running tools, and coordinated multi-agent workflows.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 80.8
Strong agentic and computer-use capability with broad cloud and API access is counterbalanced by improved alignment and measured prompt-injection defenses.
News tied to Claude Opus 4.5
The model score of 80.8 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Frontier models gain physical control when paired with pretrained robot policies
Anthropic evaluated twelve models from five providers across simulated and physical robotics tasks. Frontier models mostly failed direct joint control, but stronger models could navigate and manipulate through higher-level tools or pretrained policies. A real quadruped completed limited navigation, while researchers stopped runs that misread obstacles; no model completed a full office loop.
- Full item contribution
- +0.13
- Claude Opus 4.5 equal share
- +0.02
Anthropic reports production safety training that suppresses agentic misalignment
Anthropic reported that difficult-advice training reduced agentic misalignment to zero in its evaluation and that constitution-based documents generalized beyond their training distribution. The techniques were applied to production models beginning with Claude Opus 4.5, with explicit warnings that the tests cannot guarantee safety.
- Full item contribution
- -0.24
- Claude Opus 4.5 equal share
- -0.04
Ajeya Cotra raises her 2026 AI-agent capability forecast
Ajeya Cotra said Claude Opus 4.6's roughly 12-hour METR time horizon made her January forecast too conservative, and revised her year-end expectation to more than 100 hours on comparable software tasks while stressing wide uncertainty.
- Full item contribution
- +0.19
- Claude Opus 4.5 equal share
- +0.10
Anthropic deploys stronger browser-agent prompt-injection defenses
Anthropic combined Claude Opus 4.5 training, content classifiers, intervention logic, and continuous red teaming to reduce adaptive prompt-injection attack success to about one percent and expanded Claude for Chrome to beta.
- Full item contribution
- -0.14
- Claude Opus 4.5 equal share
- -0.14
Claude Opus 4.5 expands long-running agents and computer use
Anthropic released Claude Opus 4.5 across its apps, API, and major clouds with stronger coding, computer use, tool orchestration, multi-agent coordination, and longer-running workflows.
- Full item contribution
- +0.21
- Claude Opus 4.5 equal share
- +0.21
Model score history
-
R4
Doom Score 80.8
Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 80.8
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 78.2
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 72.1
New exact model profile from dated launch, system card, and deployed safeguard report.
11 Aug 2026